13592results about "2D-image generation" patented technology

An example operation may include one or more of generating a unique image based on execution of an image generating model and displaying the unique image via a user interface of a software application, assigning a segment of the unique image to a goal at a first point in time based on user inputs via a user interface of the software application, monitoring account activity of a user within the software application, determining, at a second point in time, that the user is closer to the goal based on the monitored account activity of the user within the software application, and in response to the determination, increasing a size of the segment of the unique image assigned to the goal of the user.

The invention discloses an MRI medical image correction method and system based on a convolutional neural network and a computer readable storage medium, and the method comprises the steps: obtaining a brain MRI medical image, and carrying out the preprocessing; extracting lesion features of the brain lacuna infarction from the preprocessed MRI medical image through a convolutional neural network, and positioning a lesion area of the brain lacuna infarction; performing detail enhancement on the lesion area of the cerebral lacuna infarction, segmenting the lesion area and optimizing a segmentation result; and carrying out artifact restoration on the segmented image, and generating a three-dimensional focus visualization model based on the restored image. According to the method, through processing in multiple aspects such as quality evaluation, lesion recognition, segmentation, artifact repair and three-dimensional visualization of the MRI image, the lesion area can be recognized more efficiently and accurately, the image quality is improved, and an efficient and accurate brain lacuna infarction diagnosis auxiliary tool is provided.

The invention relates to the technical field of image detection, in particular to a PCBA board defect detection method and system based on image processing, and the method comprises the following steps: carrying out the meshing calculation of a gray scale deviation after a gray scale image is subjected to Gaussian filtering denoising, generating change rate data, carrying out the statistics of a frequency number, constructing a histogram, combining with an Otsu algorithm, and generating a candidate mask; extracting pixels based on a mask, calculating a gradient modulus, screening edge candidate points, carrying out gradient direction connection and morphological processing to generate a complete edge structure, expanding a connected domain through a region growing algorithm, aligning the connected domain with a template contour, and outputting defect coordinates. According to the method, the defect identification sensitivity is improved through combination of gray level image gridding processing and dynamic threshold calculation, a candidate mask is generated through grid gray level change rate statistics and an Otsu algorithm to avoid over-segmentation missing detection, and the contour precision is improved through combination of gradient modulus difference screening and morphological closed operation optimization. The region growing algorithm and template dynamic alignment reduce deformation misjudgment, and staged dimension reduction and feature enhancement reduce calculation complexity and solve resource waste.

Image series transformation for optimal compressibility is performed with neural upsampling and error resilience. A novel correlation network composed of convolutional layers for feature extraction that extract multi-dimensional features from the image and a channel-wise transformer with attention to capture complex inter-channel dependencies. An angle optimizer enhances compressibility of an image and an error resilience subsystem improves robustness against transmission errors and data loss. The error resilience subsystem applies forward error correction coding, data partitioning based on importance, and embeds error concealment hints. This hybrid approach addresses both local and global features, mitigates compression artifacts, improves image quality, and enhances data integrity during transmission. The correlation network incorporates error correction and concealment techniques during decoding. The model's outputs enable effective image reconstruction, achieving advanced compression while preserving information for accurate analysis.

A computer-implemented method for generating an image involves receiving input text and layout information, decomposing the text into global and local features, and encoding these features into vectors. The method initializes an initial image representation and uses a trained neural network to predict global noise from the global vector and initial image representation. It also predicts initial local noise for each local feature using their respective vectors and the initial image representation. The final local noise for each feature is determined using the initial local noise and the global noise. The predicted global and final local noises are combined based on the layout information. Finally, the initial image representation is denoised using this combined noise to produce the next image representation, ultimately generating the image.

Embodiments are disclosed for editing video using image diffusion. The method may include receiving an input video depicting a target and a prompt including an edit to be made to the target. A keyframe associated with the input video is then identified. The keyframe is edited, using a generative neural network, based on the prompt to generate an edited keyframe. A subsequent frame of the input video is edited using the generative neural network, based on the prompt, features of the edited keyframe, and features of an intervening frame to generate an edited output video.

Embodiments described herein provide a video generation framework built on a decoupled multimodal cross-attention module to simultaneously condition the generation on both an input image and a text input. The video generation may thus be conditioned on the visual appearance of a target object reflected in the input image. In this way, zero-shot video generation may be achieved with little fine-tuning efforts.

Apparatuses, processors, computing systems, devices, non-transitory computer medium, and / or methods for using neural networks for generating multiple related images. In at least one embodiment, a processor includes circuitry to use one or more neural networks to generate several images, where each image includes a same object (e.g., same subject) and different backgrounds. For example, a processor including one or more circuits to use one or more neural networks to generate one or more objects (e.g., an animal, a vehicle, a person) within two or more different images (e.g., different backgrounds such as weather, season, environment) based, at least in part, on one or more indications (e.g., text prompts) by one or more users indicating content of at least one of the two or more different images (e.g., objects and / or backgrounds for each image in text such as adjectives and nouns) other than the one or more objects.

Toggling between different arrangements of discrete graphical elements conveying representations of alphanumeric data in a non-alphanumeric manner includes: causing an initial arrangement of tiles on a display. The tiles are associated with items including first and second characteristics having first and second alphanumeric values, and each item is associated with a common objective. Each tile adopts first and second visual characteristics. The tiles are grouped based on the second visual characteristics, and are arranged to visualize progress toward the common objective. In response to a trigger, underlying first alphanumeric values of each item are aggregated on a grouping-by-grouping basis, and the groupings are merged into an associated merged tile expressing the second visual characteristic. The merged tiles have different sizes based on the aggregating of the underlying associated first alphanumeric values. The merged tiles are presented on the display by juxtaposing them using the second set of visual characteristics.

A method, apparatus, non-transitory computer readable medium, and system for generating synthetic videos includes obtaining an input prompt describing a video scene. The embodiments then generate a plurality of frame-wise token embeddings corresponding to a sequence of video frames, respectively, based on the input prompt. Subsequently, embodiments generate, using a video generation model, a synthesized video depicting the video scene. The synthesized includes a plurality of images corresponding to the sequence of video frames.

The subject technology includes an image generator that generates images having specific visual concepts. The image generator uses a selective training process to fine-tune a text to a image generative system. The constrained text to image generative system may be trained to understand multiple custom tokens that embody visual characteristics of images included in fine-tuning datasets. Image generation prompts including one or more custom tokens may be used to condition the image creation process of the constrained text to image system to produce synthetic images having improved specificity, more creativity, and higher performance. Images created by the constrained text to image system may be ranked based on one or more criteria to further refine the created images for one or more specific use cases.

Examples described herein relate to automatic image generation. A plurality of inputs is accessed. The inputs include first input data and second input data. The first input data includes a text prompt describing a desired image and the second input data is indicative of one or more structural features of the desired image. One or more intermediate outputs are generated via a first generative machine learning model that uses the plurality of inputs as first control signals. An output image is generated via a second generative machine learning model that uses at least a subset of the plurality of inputs and at least a subset of the one or more intermediate outputs as second control signals. The output image is presented at a user device of a user.

Certain aspects of the present disclosure provide techniques for generating an output image based on a text prompt. A method may include receiving the text prompt; providing a user interface comprising one or more input elements associated with one or more words of the text prompt; receiving input corresponding to at least one of the one or more input elements, the input indicating a semantic importance for each of at least one of the one or more words associated with the at least one of the one or more input elements; and generating the output image based on the text prompt and the input.

The invention relates to a coastal wetland ecological restoration effect evaluation method and system, and belongs to the technical field of ecological monitoring and restoration. Aiming at the problems of static evaluation index lag, insufficient data fragmentation integration and lack of causal diagnosis mechanism in the prior art, multi-source time sequence ecological data are acquired by constructing a three-dimensional monitoring network consisting of satellite remote sensing, an unmanned aerial vehicle, an Internet of Things sensor and an underwater robot; a fusion data set is generated based on space-time alignment and tidal phase marking, dynamic evolution characteristics are extracted by using an LSTM network, and a spatial distribution difference chart of ecological parameters before and after restoration is generated in combination with a GAN; and furthermore, through hot area clustering and historical data association mining, a degradation driving factor is positioned, and an optimization suggestion is generated. The method breaks through the space-time limitation of a traditional evaluation method, remarkably improves the degradation diagnosis precision and the regulation and control efficiency of restoration engineering, and is suitable for various ecological restoration scenes such as estuary delta and coral reefs.

The invention discloses a low-dose CT reconstruction method and system based on global optimization iteration deep learning, and the method comprises the steps: collecting CT cross section data of a normal dose, and generating low-dose CT data; the method comprises the following steps: establishing a dual-domain analysis compression iteration model, constructing maximum posteriori estimation based on a CT projection chordal graph data composite Poisson noise generation mechanism, subdividing CT projection data into a projection domain and a chordal graph domain, sequentially updating the projection data, the chordal graph data and image data, and constructing an iteration algorithm to realize CT global optimization modeling. Expanding an iterative algorithm into a trained reconstruction network; inputting the paired data into the expanded network for training, and storing a model with the minimum output result loss; a sub-network and an attention mechanism are added for CT data features, jump connection weights are finely adjusted, middle layer neural network parameters are finely adjusted and updated through middle supervision, and a global optimization iteration deep learning model NGACI-Net is obtained. According to the method, the problems that the low-dose CT image quality is poor, the reconstruction efficiency is low, and generalization and interpretability are lacked are solved.

The invention discloses an AI-based animation split script automatic generation and visual preview method and system, and the method comprises the following steps: 1, receiving a natural language script text inputted by a user, the natural language script text comprising scene description, role action, dialogue and shot indication information; step 2, performing semantic analysis and structured analysis on the script text based on a natural language processing technology, and identifying and extracting key narrative elements; by introducing an artificial intelligence technology, end-to-end automatic generation and interactive optimization from a character script to a dynamic split rehearsal video are realized, the system can deeply understand scenes, actions, role emotions and shot languages in the script, corresponding visual elements are automatically matched and generated, and the dynamic split rehearsal effect is improved. And the timeline and the rhythm conforming to the film and television grammar are constructed, so that the efficiency and the consistency of the split creation are greatly improved, and the professional threshold and the manufacturing cost are reduced.

The invention relates to the field of natural language processing. The invention discloses a cross-modal knowledge optimization system for improving localization adaptability of a large language model, and the system comprises a modal data collection module which collects cross-modal localization data of characters, audios and videos; the data preprocessing module is connected with the data acquisition module and preprocesses acquired data; the cross-modal knowledge fusion module is connected with the preprocessing module, fuses data and large language model general knowledge, and performs mining association by means of a cross-modal learning algorithm to form a localized cross-modal knowledge graph; the model fine-tuning module is connected with the fusion module and uses the map to finely tune the large language model; the evaluation feedback module is connected with the fine tuning module and evaluates the localization performance of the model. Through multi-modal data integration, dynamic preprocessing, deep knowledge fusion, efficient fine adjustment and intelligent feedback, various problems in the large language model localization process are systematically solved, and the expression of the model in dialect understanding, cultural questions and answers and cross-modal tasks is remarkably improved.

A method and an electronic device for generating article content are disclosed. The method includes: constructing a subject keyword library by collecting industry trend data, and collecting content materials for article generation; in response to a request for generating an industry information article, determining a target subject keyword and a prompt word text for dialogue with an artificial intelligence AI large language model, to facilitate a generation of an article subject; screening multiple segments of target content materials from the content materials; constructing a prompt word text for dialogue with the AI large language model according to the article subject and the target content materials to generate an article outline, the article outline including multiple sub-subjects; and calling the AI large language model multiple times to generate corresponding text contents for the multiple sub-subjects respectively.

A second input image is generated by applying a target augmented reality (AR) effect to a first input image. The first input image and the second input image are provided to a first visual-semantic machine learning model to obtain output describing at least one feature of the target AR effect. The first visual-semantic machine learning model is fine-tuned from a second visual-semantic machine learning model by using training samples. Each training sample comprises a first training image, a second training image, and a training description of a given AR effect. The second training image is generated by applying the given AR effect to the first training image. A description of the target AR effect is selected based on the output of the visual-semantic machine learning model. The description of the target AR effect is stored in association with an identifier of the target AR effect.

The invention discloses a remote sensing image generation method based on a federal visual language model, which belongs to the technical field of machine learning and specifically comprises the following steps: receiving text instruction description by each client; extracting a multi-scale feature map from private remote sensing image data through a visual encoder, and generating a semantic embedding vector by text instruction description through a language encoder; inputting the semantic embedding vector and the multi-scale feature map into a dynamic attention mask generator to generate pixel-level space weight distribution; carrying out weighted fusion operation on the multi-scale feature map, and generating visual feature representation of text conditionalization; generating a remote sensing image according with the description of the text instruction through an image decoder; the client uploads model parameter increments of the visual encoder, the language encoder and the dynamic attention mask generator to the central server; the central server aggregates the model parameter increments, and distributes the updated global model parameters to each client; according to the method, the flexibility and semantic consistency of remote sensing image generation are effectively improved.

The invention provides a tunnel construction structure health on-line monitoring method and system, and the method comprises the steps: obtaining stress data, crack images and seismic wave signals of tunnel construction, and carrying out the preprocessing; obtaining and constructing stress-crack joint representation mapping, generating a first joint feature vector, and predicting a lining health state of a future # imgabs0 # time step; generating a second joint feature vector, and determining a stratum stress field of the future # imgabs1 # time step according to the second joint feature vector; constructing a tunnel lining damage probability model according to the stress data and the crack image, and determining an overall construction risk score; and dividing the construction risks into a plurality of grades. According to the method, data multi-modal fusion, structure-stratum joint modeling and AI enhanced prediction and early warning are achieved, the defects in the prior art are effectively overcome, the method can be widely applied to engineering scenes such as tunnel construction, subway construction and underground space development, and the construction safety and the structure health monitoring capacity are remarkably improved.

Implementations relate to a method implemented by one or more processors, the method including: receiving an input prompt for a large language model (LLM); generating first LLM output that is usable to generate a set of user interface (UI) each associated with a corresponding sub-prompt of the input prompt; causing, based on the first LLM output, the set of UI elements to be rendered at a user device; receiving further user input based on user interactions with one or more of the UI elements of the set of UI elements; and in response to determining that one or more termination conditions are satisfied: generating a final response to the input prompt based on generating second LLM output that is usable to generate the final response; and causing the final response to be rendered at the user device.

A method includes adding an outpaint mask to an image to generate a masked image. The method also includes processing the image using an encoder neural network to generate an image representation of the image in a latent space. The method further includes processing the masked image using a convolution neural network and adding the image representation to generate an image embedding. The method also includes processing the image representation and the image embedding using at least one of a diffusion model and an interpolation process to generate a noisy latent image representation. The method further includes using a large language model to contextualize an outpainting prompt. The method also includes denoising the noisy latent image representation based on the contextualized outpainting prompt to generate a denoised latent image representation. In addition, the method includes processing the denoised latent image representation using a decoder neural network to generate an outpainted image.

The invention discloses an interactive drawing generation method, system and device based on artificial intelligence, relates to the technical field of artificial intelligence, and realizes the generation of a high-quality image through multi-modal data fusion, semantic alignment, conflict detection and iterative correction. The scheme comprises the following core steps: acquiring multi-modal data such as texts, voices, sketches and the like, and processing the multi-modal data into a formatted feature data set; performing alignment and weighted fusion on the multi-modal features to generate unified semantic space features; detecting semantic inconsistency of the image and text description by using a vision-text attention mechanism, generating a conflict index matrix and triggering an alarm mark; and iteratively correcting the generated image based on the unified semantic space features, the conflict index matrix and the alarm marks. The system is composed of a data acquisition and preprocessing module, a multi-modal feature alignment and fusion module, a conflict detection and alarm module, an image generation and iterative correction module, a system control and scheduling module and the like.

Embodiments include a system for determining cardiovascular information for a patient. The system may include at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the patient's heart based on the patient-specific data. The at least one computer system may be further configured to create a physics-based model relating to a blood flow characteristic of the patient's heart and determine a fractional flow reserve within the patient's heart based on the three-dimensional model and the physics-based model.

Various implementations disclosed herein include devices, systems, and methods that present content items (e.g., movies, TV shows, home-made videos, etc.) on electronic devices such as HMDs. Some implementations adjust what is being displayed by the electronic devices to mitigate optical module-based artifacts (e.g., ghosting). For example, in an HMD with a catadioptric lens, a mirror layer may leak some light to produce ghosting artifacts that may be mitigated by adjusting brightness, dynamic range, contrast, light-spill, color, etc. Some implementations utilize adjustments that are based on content item awareness (e.g., adjustments based on the peak brightness of the scene in a movie that is being displayed within an extended reality (XR) environment, etc.). Some implementations provide adjustments based on environment awareness (e.g., how dark is the surroundings or pass-through environment) and / or optical module modeling. The adjustments may change a particular content item and / or an environment in which it is presented.

The invention discloses a deconvolution-based full-focusing super-resolution imaging method, and relates to the technical field of full-focusing super-resolution imaging, and the method specifically comprises the steps: 1, carrying out the data collection based on a full-matrix collection mode, and carrying out the initial image reconstruction through a full-focusing method, and 2, carrying out the reconstruction of an initial image through the analysis of a point spread function of an imaging system, the method comprises the following steps: step 1, establishing a physical convolution model to describe a fuzzy effect in an imaging process, and step 2, by taking minimization of an imaging error as a target and introducing sparse constraint, promoting generation of non-zero reaction only at a position where a defect actually exists in a reconstructed image and inhibiting background noise and artifacts. A point spread function modeling imaging process is introduced, sparse deconvolution solution is carried out on defect distribution by utilizing a fast iteration threshold method, and a super-resolution imaging scheme which has a physical basis and is high in robustness and calculation efficiency is provided for guided wave ultrasonic imaging.

Systems and methods are provided for providing package delivery assistance. The systems and methods detect, by a wearable device, an identifier associated with a package and retrieve package delivery information from a package delivery device using the identifier of the package. The systems and methods display, by the wearable device, a portion of the package delivery information and generate, by the wearable device, visual navigational assistance to guide a courier to a delivery location associated with the package.

Disclosed are an electronic system for controlling a memo object in a virtual space and an operating method thereof. The disclosed electronic system comprises: an electronic device, which detects, on the basis of an input from a user, the motion of writing on a reference object in a virtual space; and a display device, which displays a scene in the virtual space corresponding to the viewpoint of the user and provides the scene to the user and, in response to the case where the reference object is included in the scene, displays on the reference object the writing corresponding to the writing motion, on the basis of information transmitted from the electronic device, wherein the reference object in the virtual space is disposed on the surface of the electronic device, at least one of the two hands of the user is tracked and displayed in the virtual space, and the tracked hand of the user controls one or more objects in the virtual space.

Disclosed are a method, system, and device for removing smoke from laparoscope images based on a conditional diffusion model. The method includes: segmenting a video of a laparoscopic surgery according to the number of frames to form a data set; performing smoke rendering on the obtained laparoscope smokeless images, and synthesizing paired smoky images to obtain a synthetic data set containing the smokeless images and the smoky images; inputting the smokeless images into the conditional diffusion model for forward noise addition, and continuously adding noise until the smokeless images are completely noised; inputting the smoky images into a smoke sensing module to obtain smoke concentration and position information, then training a neural network, and continuously performing reverse denoising on the completely noised images using the trained neural network until clear smokeless images are outputted; and optimizing a smoke removal model through a multi-loss function fusion strategy.